← Back to community benchmarks

Qwen3.6-35B-A3B

M3 Max (30c) · 96 GB · 4bit · 2026-04-30

Performance

4k

tokens

1,140

PP tok/s

83.0

TG tok/s

3594

TTFT (ms)

20.0

Peak mem (GB)

Hardware

Chip M3 Max (30c)

Memory 96 GB

GPU Cores 30

Software

oMLX v0.3.8

macOS macOS 26.4.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	931.4	86.3	19.3 GB	view
4k	1,140	83.0	20.0 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	86.3	1.00×
2×	132.4	1.53×
4×	152.5	1.77×